[PATCH v2 REPOST] fscache: Use only one fscache_object_cong_wait.

[Sebastian Andrzej Siewior]

In the commit mentioned below, fscache was converted from slow-work to
workqueue. slow_work_enqueue() and slow_work_sleep_till_thread_needed()
did not use a per-CPU workqueue. They choose from two global waitqueues
depending on the SLOW_WORK_VERY_SLOW bit which was not set so it always
one waitqueue.

I can't find out how it is ensured that a waiter on certain CPU is woken
up be the other side. My guess is that the timeout in schedule_timeout()
ensures that it does not wait forever (or a random wake up).

fscache_object_sleep_till_congested() must be invoked from preemptible
context in order for schedule() to work. In this case this_cpu_ptr()
should complain with CONFIG_DEBUG_PREEMPT enabled except the thread is
bound to one CPU.

wake_up() wakes only one waiter and I'm not sure if it is guaranteed
that only one waiter exists.

Replace the per-CPU waitqueue with one global waitqueue.

Fixes: 8b8edefa2fffb ("fscache: convert object to use workqueue instead of slow-work")
Reported-by: Gregor Beck <gregor.beck@xxxxxxxxx>
Cc: stable-rt@xxxxxxxxxxxxxxx
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
---
Previous post
  https://lore.kernel.org/all/20211029083839.xwwt7jgzru3kcpii@xxxxxxxxxxxxx/

 fs/fscache/internal.h |    1 -
 fs/fscache/main.c     |    6 ------
 fs/fscache/object.c   |   13 +++++--------
 3 files changed, 5 insertions(+), 15 deletions(-)

--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -81,7 +81,6 @@ extern unsigned fscache_debug;
 extern struct kobject *fscache_root;
 extern struct workqueue_struct *fscache_object_wq;
 extern struct workqueue_struct *fscache_op_wq;
-DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
 
 extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n);
 
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -41,8 +41,6 @@ struct kobject *fscache_root;
 struct workqueue_struct *fscache_object_wq;
 struct workqueue_struct *fscache_op_wq;
 
-DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait);
-
 /* these values serve as lower bounds, will be adjusted in fscache_init() */
 static unsigned fscache_object_max_active = 4;
 static unsigned fscache_op_max_active = 2;
@@ -138,7 +136,6 @@ unsigned int fscache_hash(unsigned int s
 static int __init fscache_init(void)
 {
 	unsigned int nr_cpus = num_possible_cpus();
-	unsigned int cpu;
 	int ret;
 
 	fscache_object_max_active =
@@ -161,9 +158,6 @@ static int __init fscache_init(void)
 	if (!fscache_op_wq)
 		goto error_op_wq;
 
-	for_each_possible_cpu(cpu)
-		init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu));
-
 	ret = fscache_proc_init();
 	if (ret < 0)
 		goto error_proc;
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -798,6 +798,8 @@ void fscache_object_destroy(struct fscac
 }
 EXPORT_SYMBOL(fscache_object_destroy);
 
+static DECLARE_WAIT_QUEUE_HEAD(fscache_object_cong_wait);
+
 /*
  * enqueue an object for metadata-type processing
  */
@@ -806,16 +808,12 @@ void fscache_enqueue_object(struct fscac
 	_enter("{OBJ%x}", object->debug_id);
 
 	if (fscache_get_object(object, fscache_obj_get_queue) >= 0) {
-		wait_queue_head_t *cong_wq =
-			&get_cpu_var(fscache_object_cong_wait);
 
 		if (queue_work(fscache_object_wq, &object->work)) {
 			if (fscache_object_congested())
-				wake_up(cong_wq);
+				wake_up(&fscache_object_cong_wait);
 		} else
 			fscache_put_object(object, fscache_obj_put_queue);
-
-		put_cpu_var(fscache_object_cong_wait);
 	}
 }
 
@@ -833,16 +831,15 @@ void fscache_enqueue_object(struct fscac
  */
 bool fscache_object_sleep_till_congested(signed long *timeoutp)
 {
-	wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait);
 	DEFINE_WAIT(wait);
 
 	if (fscache_object_congested())
 		return true;
 
-	add_wait_queue_exclusive(cong_wq, &wait);
+	add_wait_queue_exclusive(&fscache_object_cong_wait, &wait);
 	if (!fscache_object_congested())
 		*timeoutp = schedule_timeout(*timeoutp);
-	finish_wait(cong_wq, &wait);
+	finish_wait(&fscache_object_cong_wait, &wait);
 
 	return fscache_object_congested();
 }